Bounds of optimal learning.

Belavkin, Roman V. ORCID logoORCID: (2009) Bounds of optimal learning. In: 2009 IEEE International Symposium on Adaptive Dynamic Programming and Reinforcement Learning, March 30 – April 2, 2009, Sheraton Music City Hotel, Nashville, TN, USA. . [Conference or Workshop Item]

Download (167kB) | Preview


Learning is considered as a dynamic process described by a trajectory on a statistical manifold, and a topology is introduced defining trajectories continuous in information. The analysis generalises the application of Orlicz spaces in non-parametric information geometry to topological function spaces with asymmetric gauge functions (e.g. quasi-metric spaces defined in terms of KL divergence). Optimality conditions are formulated for dynamical constraints, and two main results are outlined: 1) Parametrisation of optimal learning trajectories from empirical constraints using generalised characteristic potentials; 2) A gradient theorem for the potentials defining optimal utility and information bounds of a learning system. These results not only generalise some known relations of statistical mechanics and variational methods in information theory, but also can be used for optimisation of the exploration-exploitation balance in online learning systems.

Item Type: Conference or Workshop Item (Paper)
Research Areas: A. > School of Science and Technology > Computer Science
A. > School of Science and Technology > Computer Science > Artificial Intelligence group
Item ID: 3489
Useful Links:
Depositing User: Dr Roman Belavkin
Date Deposited: 24 Mar 2010 14:08
Last Modified: 30 Nov 2022 01:25

Actions (login required)

View Item View Item


Activity Overview
6 month trend
6 month trend

Additional statistics are available via IRStats2.